Language dependent universal phoneme posterior estimation for mixed language speech recognition

Citations Over TimeTop 10% of 2011 papers

Abstract

This paper presents a new approach to estimate "universal" phoneme posterior probabilities for mixed language speech recognition. More specifically, we propose a new theoretical framework to combine phoneme class posterior probabilities in a principled way by using (statistical) evidence about the language identity. We investigate the proposed approach in a mixed language environment (Speech-Dat(II)) consisting of five European languages. Our studies show that the proposed approach can yield significant improvements on a mixed language task, while maintaining the performance on monolingual tasks. Additionally, through a case study, we also demonstrate the potential benefits of the proposed approach for non-native speech recognition.

Related Papers

• → Improved topic-dependent language modeling using information retrieval techniques(1999)55 cited
• Weighted posterior probability output for support vector machines(2007)
• A Method of Imbedding-Augmenting and Some Properties of Multi-Identity Rings(2001)
• HYPERREAL IDENTITY IN FRANK WILLIAM ABAGNALE'S NOVEL CATCH ME IF YOU CAN(2006)
• → Is it identity all the way down? From supersubstantivalism to composition as identity and back again(2020)